ModelBeat
Models/Nemotron 3-Nano-30B-A3B
All models
N

NVIDIA: Nemotron 3-Nano-30B-A3B

nvidia/nemotron-3-nano-30b-a3b

Nemotron 3-Nano-30B-A3B is NVIDIA’s open-weights AI model, released Dec 15, 2025. It costs $0.05/M input and $0.20/M output tokens, and handles a 262K-token context window.

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.

Context
262K
Input
$0.05 / 1M
Output
$0.20 / 1M
Released
Dec 15, 2025
Modalities
texttext

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Nemotron 3-Nano-30B-A3B lands among all models tracked on Model Beat.

No standardized benchmark scores from Epoch AI yet — common for very recent, image, or niche models. Scores appear here once published.

In the news

1

Changelog

2
  • Nemotron 3-Nano-30B-A3B: cheapest credible provider via Crusoe now $0.05 per 1M input tokens (was $0.06, -17%)cheapest provider · Jul 26, 2026
  • Nemotron 3-Nano-30B-A3B: cheapest credible provider via Crusoe now $0.2 per 1M output tokens (was $0.24, -17%)cheapest provider · Jul 26, 2026

Compare Nemotron 3-Nano-30B-A3B with

Frequently asked questions

What is Nemotron 3-Nano-30B-A3B?

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.

Who created Nemotron 3-Nano-30B-A3B?

Nemotron 3-Nano-30B-A3B is an AI model developed by NVIDIA, part of the Nemotron family, released Dec 15, 2025.

How much does Nemotron 3-Nano-30B-A3B cost?

Nemotron 3-Nano-30B-A3B is served from $0.05 per million input tokens and $0.20 per million output tokens (cheapest credible provider on OpenRouter: Crusoe).

What is Nemotron 3-Nano-30B-A3B's context window?

Nemotron 3-Nano-30B-A3B supports a context window of up to 262K tokens.

Is Nemotron 3-Nano-30B-A3B open source?

Nemotron 3-Nano-30B-A3B is released with open weights (Open weights (restricted use)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Jul 30, 2026.